Training in progress, step 25000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00cb98eb1da63ba4189d4b55310bd43816969d50531865b7774f8fdcf202af6a
+oid sha256:e4a556b743de53b81786a2c97c189b8ab38eaa9b1b15213d74592f6e5df0ee9b
 size 242041896

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1827f3ba86066e05a7c8d0cf70bf3fefd44d3648c1da02dcd8f3c00a2aece1c
+oid sha256:07f36edfb9a4f724f199b1d822cf88054f24aa8663e46816caef2402d04ec3c8
 size 484163514

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76200746e0093b7cc6d3809d80c9ea53532cb8fe856e4e289194263f281b138c
+oid sha256:4466b7aec0280a011a8c4d08d66796961b3a1f1e19e62b4a4a1b3bce38987c6c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4ff7878a46fca2f7284f626205121313e31cd4872637223f000f97e21368d0
+oid sha256:f3237be099a38adc6de0eebdf22fb3fe78ade2edb6a766c16e20254df2789831
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.759975445058318,
+  "epoch": 3.83670963781461,
   "eval_steps": 500,
-  "global_step": 24500,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -331,13 +331,19 @@
       "learning_rate": 0.0002483118477593616,
       "loss": 0.4896,
       "step": 24500
+    },
+    {
+      "epoch": 3.84,
+      "learning_rate": 0.00023296500920810313,
+      "loss": 0.4832,
+      "step": 25000
     }
   ],
   "logging_steps": 500,
   "max_steps": 32580,
   "num_train_epochs": 5,
   "save_steps": 500,
-  "total_flos": 1.2986967867260928e+16,
+  "total_flos": 1.325300755464192e+16,
   "trial_name": null,
   "trial_params": null
 }